Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/671442
Title: Shape guided object segmentation
Authors: Borenstein, Eran;Malik, Jitendra
subject: Science & Technology
Year: 2008
Abstract: We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.
Description: 

URI: http://localhost/handle/Hannan/368785
http://localhost/handle/Hannan/671442
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL508353.pdf1.13 MBAdobe PDF
Title: Shape guided object segmentation
Authors: Borenstein, Eran;Malik, Jitendra
subject: Science & Technology
Year: 2008
Abstract: We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.
Description: 

URI: http://localhost/handle/Hannan/368785
http://localhost/handle/Hannan/671442
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL508353.pdf1.13 MBAdobe PDF
Title: Shape guided object segmentation
Authors: Borenstein, Eran;Malik, Jitendra
subject: Science & Technology
Year: 2008
Abstract: We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object’s shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.
Description: 

URI: http://localhost/handle/Hannan/368785
http://localhost/handle/Hannan/671442
Appears in Collections:2002-2008

Files in This Item:
File SizeFormat 
AL508353.pdf1.13 MBAdobe PDF